Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    hello? the primary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     നിൽ
    0.37
     declaró
    0.36
     |-
    0.36
     naar
    0.35
    gek
    0.34
    延长
    0.34
    隠
    0.34
     Lake
    0.33
     [{
    0.33
     सदस्यों
    0.33
    POSITIVE LOGITS
    ၾ
    0.41
    ultipl
    0.37
     comida
    0.37
    特定的
    0.36
     требований
    0.36
     જરૂરી
    0.36
    υπ
    0.36
    共有
    0.36
     comidas
    0.36
     Worship
    0.35
    Act Density 0.001%

    No Known Activations